Performance of k-means based satellite image clustering in RGB and HSV color space

This paper throws a light on the available clustering techniques and algorithms, k-means is used to cluster standard and satellite image in RGB and HSV color space. Normally satellite images comes with data and noises, in order to extract meaningful information efficiently there is a need of image clustering and performance of clustering based on pixel classification is greatly affected by the color space we selected, because image analysis in terms of Red, Green and Blue components is more difficult as compared to in terms of hue, saturation and value in context of differentiation an object. Our analysis of image clustering in two different color spaces using the k-means technique shows that clustering performance decreases with RGB color space when compared to HSV color space. CHI, DBI and SE i ndexes are calculated and compared.